Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

CAGNet: Content-Aware Guidance for Salient Object Detection

About

Beneficial from Fully Convolutional Neural Networks (FCNs), saliency detection methods have achieved promising results. However, it is still challenging to learn effective features for detecting salient objects in complicated scenarios, in which i) non-salient regions may have "salient-like" appearance; ii) the salient objects may have different-looking regions. To handle these complex scenarios, we propose a Feature Guide Network which exploits the nature of low-level and high-level features to i) make foreground and background regions more distinct and suppress the non-salient regions which have "salient-like" appearance; ii) assign foreground label to different-looking salient regions. Furthermore, we utilize a Multi-scale Feature Extraction Module (MFEM) for each level of abstraction to obtain multi-scale contextual information. Finally, we design a loss function which outperforms the widely-used Cross-entropy loss. By adopting four different pre-trained models as the backbone, we prove that our method is very general with respect to the choice of the backbone model. Experiments on five challenging datasets demonstrate that our method achieves the state-of-the-art performance in terms of different evaluation metrics. Additionally, our approach contains fewer parameters than the existing ones, does not need any post-processing, and runs fast at a real-time speed of 28 FPS when processing a 480 x 480 image.

Sina Mohammadi, Mehrdad Noori, Ali Bahri, Sina Ghofrani Majelan, Mohammad Havaei• 2019

Related benchmarks

TaskDatasetResultRank
Salient Object DetectionDUTS (test)
M (MAE)0.04
325
Salient Object DetectionECSSD
MAE0.037
222
Salient Object DetectionPASCAL-S
MAE0.066
196
Salient Object DetectionHKU-IS
MAE0.03
175
Salient Object DetectionDUT-OMRON
MAE0.054
133
Showing 5 of 5 rows

Other info

Follow for update